WeSpeaker ResNet34 LM — MLX MLX compatible weights for WeSpeaker ResNet34 LM, converted from the pyannote speaker embedding model with BatchNorm fused into Conv2d. Model WeSpeaker ResNet34 LM is a speaker embedding model (~6.6M params) that produces 256 dimensional L2 normalized speaker embeddings from audio. Trained on VoxCeleb for speaker verification and diarization. Architecture: BatchNorm is fused into Conv2d at conversion time — no BN layers in the MLX model. Usage (Swift / MLX) Part of speech swift. Conversion Converts the original pyannote/wespeaker voxceleb resnet34 LM checkpoint using a custom unpickler (no pyannote.audio dependency required). Key transformations: Fuse BatchNorm into Conv2d: w fused = w × γ/√(σ²+ε) , b fused = β − μ×γ/√(σ²+ε) Transpose Conv2d weights: [O, I, H, W] → [O, H, W, I] for MLX channels last Rename : strip resnet. prefix, seg 1 → embedding Drop num batches tracked keys Weight Mapping PyTorch Key MLX Key Shape resnet.conv1.weight + resnet.bn1. conv1.weight [32, 3, 3, 1] resnet.layer{L}.{B}.conv{1,2}.weight + bn{1,2}. layer{L}.{B}.conv{1,2}.weight [O, 3, 3, I] resnet.layer{L}.0.shortcut.0.weight + shortcut.1. layer{L}.0.shortcut.weight [O, 1, 1, I]…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy